claude-code - 💡(How to fix) Fix Claude Code ignores its own safety hooks — violation #115 [2 comments, 3 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
anthropics/claude-code#54064Fetched 2026-04-28 06:40:12
View on GitHub
Comments
2
Participants
3
Timeline
6
Reactions
0
Author
Timeline (top)
labeled ×3commented ×2cross-referenced ×1
RAW_BUFFERClick to expand / collapse

Automated Violation Report

Claude Code edited danger zone file grammar.ts despite receiving:

  • DANGER ZONE warnings (15+ prior failed approaches)
  • MANDATORY search requirements
  • Harmonic Code Council (HCC) review warnings
  • Approach tracking warnings

Violation count this project: 115

Project: songwish-platform (Creative Life game) User complaint: Claude generates before searching, declares victory before testing, ignores its own hook warnings. Full details: https://github.com/SongWish/songwish-platform/blob/main/docs/framework/anthropic_feedback.md

What the user built to compensate:

  • 5 PreToolUse hooks (search, track, danger zone, HCC, playtest)
  • 2 PostToolUse hooks (verify removal, violation logger)
  • 4 parallel AI specialist Harmonic Code Council / HCC (Haiku API calls)
  • Automated Playwright walkthrough bot

What still fails: Claude reads warnings in system-reminder tags and proceeds without addressing them. The model treats hook output as skippable context, not mandatory gates.

Structural fix needed: PreToolUse hook warnings should require explicit acknowledgment before the edit proceeds, not just be injected as additional context.

extent analysis

TL;DR

Modify the PreToolUse hooks to require explicit acknowledgment of warnings before proceeding with edits.

Guidance

  • Review the grammar.ts file and the PreToolUse hook implementations to understand how warnings are currently being handled.
  • Update the PreToolUse hooks to block the edit process until the user or system acknowledges the warnings, rather than treating them as skippable context.
  • Consider adding a mandatory confirmation step for warnings, such as a prompt that requires a explicit response (e.g., "Acknowledge warning: yes/no") before proceeding.
  • Investigate how the model is treating hook output as context and modify it to recognize mandatory gates.

Example

No code snippet is provided as the issue does not contain specific code details.

Notes

The solution may require changes to the underlying model or the hook implementation, and may involve additional complexity to handle different types of warnings and user responses.

Recommendation

Apply workaround: Modify the PreToolUse hooks to require explicit acknowledgment of warnings, as this is a structural fix that addresses the root cause of the issue.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

claude-code - 💡(How to fix) Fix Claude Code ignores its own safety hooks — violation #115 [2 comments, 3 participants]